AI RESEARCH

Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learning

arXiv CS.LG

ArXi:2603.07898v1 Announce Type: cross Open-set active learning (OSAL) aims to identify informative samples for annotation when unlabeled data may contain previously unseen classes-a common challenge in safety-critical and open-world scenarios. Existing approaches typically rely on separately trained open-set detectors,